{"id":"https://openalex.org/W2140116426","doi":"https://doi.org/10.14778/1687627.1687750","title":"Data integration for the relational web","display_name":"Data integration for the relational web","publication_year":2009,"publication_date":"2009-08-01","ids":{"openalex":"https://openalex.org/W2140116426","doi":"https://doi.org/10.14778/1687627.1687750","mag":"2140116426"},"language":"en","primary_location":{"id":"doi:10.14778/1687627.1687750","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1687627.1687750","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039133265","display_name":"Michael Cafarella","orcid":"https://orcid.org/0000-0001-6122-0590"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Michael J. Cafarella","raw_affiliation_strings":["University of Washington, Seattle, WA","University Of Washington (Seattle, WA)"],"affiliations":[{"raw_affiliation_string":"University of Washington, Seattle, WA","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"University Of Washington (Seattle, WA)","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067621853","display_name":"Alon Halevy","orcid":"https://orcid.org/0000-0002-8717-7356"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alon Halevy","raw_affiliation_strings":["Google, Inc., Mountain View, CA","Google Inc., Mountain View, CA#TAB#"],"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountain View, CA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., Mountain View, CA#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030572958","display_name":"Nodira Khoussainova","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nodira Khoussainova","raw_affiliation_strings":["University of Washington, Seattle, WA","University Of Washington (Seattle, WA)"],"affiliations":[{"raw_affiliation_string":"University of Washington, Seattle, WA","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"University Of Washington (Seattle, WA)","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5039133265"],"corresponding_institution_ids":["https://openalex.org/I201448701"],"apc_list":null,"apc_paid":null,"fwci":31.7643,"has_fulltext":false,"cited_by_count":236,"citation_normalized_percentile":{"value":0.99584941,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"2","issue":"1","first_page":"1090","last_page":"1101"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.826636552810669},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.628982424736023},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.612074613571167},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.5727615356445312},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5291562080383301},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4989793300628662},{"id":"https://openalex.org/keywords/data-web","display_name":"Data Web","score":0.48906049132347107},{"id":"https://openalex.org/keywords/web-modeling","display_name":"Web modeling","score":0.47892460227012634},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4738716781139374},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.4592359960079193},{"id":"https://openalex.org/keywords/information-integration","display_name":"Information integration","score":0.4156913161277771},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3749263882637024},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.28439199924468994},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10029599070549011}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.826636552810669},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.628982424736023},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.612074613571167},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.5727615356445312},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5291562080383301},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4989793300628662},{"id":"https://openalex.org/C162005631","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Data Web","level":3,"score":0.48906049132347107},{"id":"https://openalex.org/C130436687","wikidata":"https://www.wikidata.org/wiki/Q7978591","display_name":"Web modeling","level":3,"score":0.47892460227012634},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4738716781139374},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.4592359960079193},{"id":"https://openalex.org/C33326189","wikidata":"https://www.wikidata.org/wiki/Q17092450","display_name":"Information integration","level":2,"score":0.4156913161277771},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3749263882637024},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.28439199924468994},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10029599070549011},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.14778/1687627.1687750","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1687627.1687750","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.151.8588","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.151.8588","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.vldb.org/pvldb/2/vldb09-576.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.934.4895","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.934.4895","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-db.deis.unibo.it/courses/SI-LS/papers4pres/CHK09.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1485156179","https://openalex.org/W1536398564","https://openalex.org/W1567365482","https://openalex.org/W1890589545","https://openalex.org/W2001959118","https://openalex.org/W2008896880","https://openalex.org/W2046020929","https://openalex.org/W2106895292","https://openalex.org/W2108223890","https://openalex.org/W2115461474","https://openalex.org/W2123845384","https://openalex.org/W2124943418","https://openalex.org/W2125822162","https://openalex.org/W2135767707","https://openalex.org/W2140602286","https://openalex.org/W2150365753","https://openalex.org/W2158188757","https://openalex.org/W2166376630","https://openalex.org/W6632351574","https://openalex.org/W6634133269","https://openalex.org/W6680646450"],"related_works":["https://openalex.org/W1495666889","https://openalex.org/W2963140294","https://openalex.org/W2100071482","https://openalex.org/W2729360854","https://openalex.org/W2780890200","https://openalex.org/W2165565716","https://openalex.org/W3088578348","https://openalex.org/W4249203355","https://openalex.org/W2121592681","https://openalex.org/W2184421161"],"abstract_inverted_index":{"The":[0,168],"Web":[1],"contains":[2],"a":[3,84,100,144,178,195,201,256],"vast":[4],"amount":[5],"of":[6,81,90,95,119,180,203,222,261,282],"structured":[7,55,207],"information":[8,122],"such":[9],"as":[10],"HTML":[11,13,69],"tables,":[12],"lists":[14],"and":[15,24,62,134,152,154,199,205,237,273,285],"deep-web":[16],"databases;":[17],"there":[18],"is":[19,57,126,173],"enormous":[20],"potential":[21],"in":[22,28,129,233],"combining":[23],"re-purposing":[25],"this":[26,35],"data":[27,33,47,56,125,150,160,208],"creative":[29],"ways.":[30],"However,":[31],"integrating":[32],"from":[34,67,162],"relational":[36],"web":[37,132],"raises":[38],"several":[39],"challenges":[40],"that":[41,146,183,229,247,287],"are":[42],"not":[43,59,231],"addressed":[44],"by":[45,225],"current":[46],"integration":[48,115],"systems":[49],"or":[50,102],"mash-up":[51],"tools.":[52],"First,":[53],"the":[54,79,82,91,107,114,120,124,166,176,185,191,211,213,217,220,223,234,238,242,268,278],"usually":[58],"published":[60],"cleanly":[61],"must":[63,110],"be":[64,74,111,137,249],"extracted":[65,138],"(say,":[66],"an":[68],"list)":[70],"before":[71],"it":[72],"can":[73,86,248],"used.":[75],"Second,":[76],"due":[77],"to":[78,136,157,174,251,255,270],"vastness":[80],"corpus,":[83],"user":[85,177,218,243,269],"never":[87],"know":[88],"all":[89],"potentially-relevant":[92],"databases":[93,109],"ahead":[94],"time":[96],"(much":[97],"less":[98],"write":[99],"wrapper":[101],"mapping":[103],"for":[104],"each":[105,281],"one);":[106],"source":[108,235],"discovered":[112],"during":[113],"process.":[116],"Third,":[117],"some":[118,260],"important":[121],"regarding":[123],"only":[127],"present":[128],"its":[130],"enclosing":[131],"page":[133],"needs":[135],"appropriately.":[139],"This":[140],"paper":[141],"describes":[142],"Octopus,":[143],"system":[145],"combines":[147],"search,":[148],"extraction,":[149],"cleaning":[151],"integration,":[153],"enables":[155],"users":[156],"create":[158],"new":[159,253],"sets":[161],"those":[163],"found":[164],"on":[165,210],"Web.":[167],"key":[169],"idea":[170],"underlying":[171,280],"Octopus":[172,258],"offer":[175],"set":[179,202],"best-effort":[181],"operators":[182,263,284],"automate":[184],"most":[186],"labor-intensive":[187],"tasks.":[188],"For":[189],"example,":[190],"Search":[192],"operator":[193,215,240],"takes":[194],"search-style":[196],"keyword":[197],"query":[198],"returns":[200],"relevance-ranked":[204],"similarity-clustered":[206],"sources":[209,224,246],"Web;":[212],"Context":[214],"helps":[216,241],"specify":[219],"semantics":[221],"inferring":[226],"attribute":[227],"values":[228],"may":[230],"appear":[232],"itself,":[236],"Extend":[239],"find":[244],"related":[245],"joined":[250],"add":[252],"attributes":[254],"table.":[257],"executes":[259],"these":[262,283],"automatically,":[264],"but":[265],"always":[266],"allows":[267],"provide":[271],"feedback":[272],"correct":[274],"errors.":[275],"We":[276],"describe":[277],"algorithms":[279],"experiments":[286],"demonstrate":[288],"their":[289],"efficacy.":[290]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":28},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":16},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":26},{"year":2014,"cited_by_count":15},{"year":2013,"cited_by_count":13},{"year":2012,"cited_by_count":18}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}